• 시스템엔지니어링학술지
• /
• 제15권2호
• /
• pp.66-71
• /
• 2019

In digital pathology, an electronic system in the biomedical domain storage of the files is a big constrain and because all the analysis and annotation takes place at every user-end manually, it becomes even harder to manage the data that is being shared inside an enterprise. Therefore, we need such a storage system which is not only big enough to store all the data but also manage it and making communication of that data much easier without losing its true from. A virtual server setup is one of those techniques which can solve this issue. We set a main server which is the main storage for all the virtual machines(that are being used at user-end) and that main server is controlled through a hypervisor so that if we want to make changes in storage overall or the main server in itself, it could be reached remotely from anywhere by just using the server's IP address. The server in our case includes XML-RPC based API which are transmitted between computers using HTTP protocol. JAVA API connects to HTTP/HTTPS protocol through JAVA Runtime Environment and exists on top of other SDK web services for the productivity boost of the running application. To manage the server easily, we use Tkinter library to develop the GUI and pmw magawidgets library which is also utilized through Tkinter. For managing, monitoring and performing operations on virtual machines, we use Python binding to XML-RPC based API. After all these settings, we approach to make the system user friendly by making GUI of the main server. Using that GUI, user can perform administrative functions like restart, suspend or resume a virtual machine. They can also logon to the slave host of the pool in case of emergency and if needed, they can also filter virtual machine by the host. Network monitoring can be performed on multiple virtual machines at same time in order to detect any loss of network connectivity.

• 한국산업정보학회논문지
• /
• 제27권6호
• /
• pp.1-12
• /
• 2022

음원 스트리밍 서비스와 Hi-Fi 시장이 성장함에 따라 다양한 음향기기들이 출시되고 있다. 이로 인해 소비자들의 제품 선택에 대한 폭은 넓어졌지만 자신의 음악적 취향과 일치하는 제품을 찾기는 더욱 어려워졌다. 본 연구에서는 사용자가 선호하는 음원으로부터 보컬 성분을 추출하고 이를 토대로 사용자에게 가장 적합한 음향기기를 추천하는 시스템을 제안하였다. 이를 위해 먼저 원본 음원을 Python의 Spleeter Library를 통해 분리하여 보컬 음원을 추출하고 제조사의 음향기기의 주파수 대역 데이터를 수집한 결과를 각각 격자 그래프로 나타내었다. 추출한 보컬 음원의 주파수 대역과 음향기기의 주파수 대역 측정치 데이터를 비교하기 위한 지표로서 Matching Gap Index(MGI)를 제안하였다. 산출된 MGI 값을 토대로 사용자 선호와의 유사도가 가장 높은 음향기기를 추천한다. 추천 결과는 음향 전문업체에서 제공하는 장르별 Equalizer 데이터를 이용하여 검증하였다.

• 방송공학회논문지
• /
• 제25권3호
• /
• pp.386-398
• /
• 2020

본 논문에서는 물체인식 딥러닝 모델을 구성하는데 필요한 데이터 레이블링 과정을 하나의 프로그램에서 사용할 수 있는 Annotation 툴을 개발했다. 프로그램의 인터페이스는 파이썬의 기본 GUI 라이브러리를 활용하였으며, 실시간으로 데이터 수집이 가능한 크롤러 기능을 구성하였다. 기존의 물체인식 딥러닝 모델인 Retinanet을 활용하여, 자동으로 Annotation 정보를 제공하는 기능을 구현했다. 또한, 다양한 물체인식 네트워크의 레이블링 형식에 맞추어 학습할 수 있도록 Pascal-VOC, YOLO, Retinanet 등 제각기 다른 학습 데이터 레이블링 형식을 저장하도록 했다. 제안하는 방식을 통해 국산 차량 이미지 데이터셋을 구축했으며, 기존의 물체인식 딥러닝 네트워크인 Retinanet과 YOLO 등에 학습하고, 정확도를 측정했다. 차량이 진입하는 영상에서 실시간으로 차량의 모델을 구별하는 정확성은 약 94%의 정확도를 기록했다.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.203-208
• /
• 2022

The occurrence of Type 2 Diabetes Mellitus (T2DM) is hoarding globally. All kinds of Diabetes Mellitus is controlled to disrupt over 415 million grownups worldwide. It was the seventh prime cause of demise widespread with a measured 1.6 million deaths right prompted by diabetes during 2016. Over 90% of diabetes cases are T2DM, with the utmost persons having at smallest one other chronic condition in UK. In valuation of contemporary applications of Big Data (BD) to Diabetes Medicare by sighted its upcoming abilities, it is compulsory to transmit out a bottomless revision over foremost theoretical literatures. The long-term growth in medicine and, in explicit, in the field of "Diabetology", is powerfully encroached to a sequence of differences and inventions. The medical and healthcare data from varied bases like analysis and treatment tactics which assistances healthcare workers to guess the actual perceptions about the development of Diabetes Medicare measures accessible by them. Apache Spark extracts "Resilient Distributed Dataset (RDD)", a vital data structure distributed finished a cluster on machines. Machine Learning (ML) deals a note-worthy method for building elegant and automatic algorithms. ML library involving of communal ML algorithms like Support Vector Classification and Random Forest are investigated in this projected work by using Jupiter Notebook - Python code, where significant quantity of result (Accuracy) is carried out by the models.

• 한국융합학회논문지
• /
• 제11권1호
• /
• pp.359-367
• /
• 2020

본 연구는 간호창업 관련 문헌에서 나타난 간호창업의 관심 주제 및 간호창업 경험의 속성, 간호창업의 방향성을 탐색하기 위해 시행되었다. MEDLINE, Embase, Cochrane Library DB를 통해 55편의 간호창업 관련 문헌을 선정하여 덱스트 네트워크 분석 방법을 적용하여 분석하였다. 분석결과 단순출현 빈도와 연결중심성에서 공통적인 핵심키워드는 'business', 'care', 'nursing', 'healthcare', 'service'으로 나타났다. 연결중심성에서 높은 순위를 보이는 키워드는 'mission', 'vision', 'team'으로 나타났다. 이에 본 연구결과가 체계적인 간호창업 교육프로그램과 간호창업 이론 개발의 기초 자료로 활용 될 수 있을 것이다.

• 센서학회지
• /
• 제29권1호
• /
• pp.19-26
• /
• 2020

Electrocardiogram (ECG) classification has become an essential task of modern day wearable devices, and can be used to detect cardiovascular diseases. State-of-the-art Artificial Intelligence (AI)-based ECG classifiers have been designed using various artificial neural networks (ANNs). Despite their high accuracy, ANNs require significant computational resources and power. Herein, three different ANNs have been compared: multilayer perceptron (MLP), convolutional neural network (CNN), and spiking neural network (SNN) only for the ECG classification. The ANN model has been developed in Python and Theano, trained on a central processing unit (CPU) platform, and deployed on a PYNQ-Z2 FPGA board to validate the model using a Jupyter notebook. Meanwhile, the hardware accelerator is designed with Overlay, which is a hardware library on PYNQ. For classification, the MIT-BIH dataset obtained from the Physionet library is used. The resulting ANN system can accurately classify four ECG types: normal, atrial premature contraction, left bundle branch block, and premature ventricular contraction. The performance of the ECG classifier models is evaluated based on accuracy and power. Among the three AI algorithms, the SNN requires the lowest power consumption of 0.226 W on-chip, followed by MLP (1.677 W), and CNN (2.266 W). However, the highest accuracy is achieved by the CNN (95%), followed by MLP (76%) and SNN (90%).

• International journal of advanced smart convergence
• /
• 제10권3호
• /
• pp.51-58
• /
• 2021

In this paper, we propose a deep learning classifier for estimating the number of layers in the Earth's structure. When installing a grounding system, knowledge of the subsurface in the area is absolutely necessary. The subsurface structure can be modeled by the earth parameters. Knowing the exact number of layers can significantly reduce the amount of computation to estimate these parameters. The classifier consists of a feedforward neural network. Apparent resistivity curves were used to train the deep learning classifier. The apparent resistivity at 20 equally spaced log points in each curve are used as the features for the input of the deep learning classifier. Apparent resistivity curve data sets are collected either by theoretical calculations or by Wenner's measurement method. Deep learning classifiers are coded by Keras, an open source neural network library written in Python. This model has been shown to converge with close to 100% accuracy.

• 스마트미디어저널
• /
• 제13권6호
• /
• pp.62-71
• /
• 2024

This study applies topic modeling to uncover user experience and app issues expressed in users' online reviews of a fan community platform, Weverse on Google Play Store. It allows us to identify the features which need to be improved to enhance user experience or need to be maintained and leveraged to attract more users. Therefore, we collect 88,068 first-level English online reviews of Weverse on Google Play Store with Google-Play-Scraper tool. After the initial preprocessing step, a dataset of 31,861 online reviews is analyzed using Latent Dirichlet Allocation (LDA) topic modeling with Gensim library in Python. There are 5 topics explored in this study which highlight significant issues such as network connection error, delayed notification, and incorrect translation. Besides, the result revealed the app's effectiveness in fostering not only interaction between fans and artists but also fans' mutual relationships. Consequently, the business can strengthen user engagement and loyalty by addressing the identified drawbacks and leveraging the platform for user communication.

• 한국항행학회논문지
• /
• 제24권3호
• /
• pp.192-197
• /
• 2020

최근 운송수단의 안전운행 및 사고방지를 목표로 하는 자율운행 관련 기술이 적극적으로 연구되고 있다. 현재 자율운행에서 장애물 탐지를 위하여 레이다 및 카메라 기술이 사용되고 있으나, 근접한 물체의 탐지 및 이격거리의 정밀계측에는 LiDAR (light detection and ranging) 센서를 사용하는 방법이 가장 적합하다. LiDAR 센서는 레이저 펄스빔을 발사하고 물체로부터 반사되어 온 반사빔과의 시간차를 취득하여 이것으로 정밀한 거리를 계산하는 측정기로, 광을 이용하기 때문에 대기환경에서 물체의 인식률이 감소할 수 있는 단점이 있다. 본 논문은 LiDAR 센서의 raw 데이타에 대한 신뢰성 향상과 이를 기반으로 실시간 주변물체에 대한 탐지 및 이격거리 계측에서 오차를 개선하기 위하여 삼각함수에 의한 포인트 cloud를 추출하고, 선형회귀 모델을 이용하여 계측알고리즘을 구현하였으며, Python 라이브러리를 활용하여 물체탐지의 오차범위를 개선할 수 있음을 검증하였다.

• 천문학회보
• /
• 제38권1호
• /
• pp.74-74
• /
• 2013

Multi-purpose Infra-Red Imaging System (MIRIS) is the main payload of the Science and Technology Satellite-3 (STSAT-3) to be launched in the late half of this year. For the Space Observation Camera (SOC) of MIRIS, we developed the data reduction pipeline with Python powered by Astropy, a community Python library for astronomy. The pipeline features the following functionalities: i) to retrieve the raw observation data from database and convert it to a FITS format, ii) to mask bad pixels, iii) to correct the non-linearity, iv) to differentiate the frames, v) to correct the flat-field, vi) to correct focal-plane distortion, vii) to improve the world coordinate system (WCS) information using known point-source catalog, and viii) to combine the sequentially taken frames. The pipeline is well modularized and has flexibility for later update. In this poster, we introduce the details of the pipeline's features and the future maintenance plan.